Related papers: MIA-Tuner: Adapting Large Language Models as Pre-t…
This paper extends the Classification Error Gauge (x-CEG) framework, originally developed for measuring the privacy-utility trade-off in tabular datasets, to privacy auditing of Large Language Models (LLMs). We propose LLM-CEG, a systematic…
In the age of agentic AI, the growing deployment of multi-modal models (MMs) has introduced new attack vectors that can leak sensitive training data in MMs, causing privacy leakage. This paper investigates a black-box privacy attack, i.e.,…
Transfer learning, successful in knowledge translation across related tasks, faces a substantial privacy threat from membership inference attacks (MIAs). These attacks, despite posing significant risk to ML model's training data, remain…
Due to limited supervised training data, large language models (LLMs) are typically pre-trained via a self-supervised "predict the next word" objective on a vast amount of unstructured text data. To make the resulting model useful to users,…
Instruction tuning -- supervised fine-tuning using instruction-response pairs -- is a key step in making pre-trained large language models (LLMs) instructable. Meanwhile, LLMs perform multitask learning during their pre-training, acquiring…
All prior membership inference attacks for fine-tuned language models use hand-crafted heuristics (e.g., loss thresholding, Min-K\%, reference calibration), each bounded by the designer's intuition. We introduce the first transferable…
As large language models (LLMs) are trained on increasingly opaque corpora, membership inference attacks (MIAs) have been proposed to audit whether copyrighted texts were used during training, despite growing concerns about their…
Large language models (LLMs) achieve remarkable advancements by leveraging tools to interact with environments, a critical step toward generalized AI. However, the standard supervised fine-tuning (SFT) approach, which relies on large-scale…
Instruction tuning is a vital step of training large language models (LLMs), so how to enhance the effect of instruction tuning has received increased attention. Existing works indicate that the quality of the dataset is more crucial than…
Detecting whether a given text is a member of the pre-training data of Large Language Models (LLMs) is crucial for ensuring data privacy and copyright protection. Most existing methods rely on the LLM's hidden information (e.g., model…
Diverse instruction data is vital for effective instruction tuning of large language models, as it enables the model to generalize across different types of inputs . Building such diversified instruction dataset is an essential step in this…
Large Language Models (LLMs) have seen widespread adoption due to their remarkable natural language capabilities. However, when deploying them in real-world settings, it is important to align LLMs to generate texts according to acceptable…
Large language models (LLMs) commonly risk copyright infringement by reproducing protected content verbatim or with insufficient transformative modifications, posing significant ethical, legal, and practical concerns. Current inference-time…
The pervasive deployment of deep learning models across critical domains has concurrently intensified privacy concerns due to their inherent propensity for data memorization. While Membership Inference Attacks (MIAs) serve as the gold…
When model developers or users fine-tune an LLM, this can induce behaviors that are unexpected, deliberately harmful, or hard to detect. It would be far easier to audit LLMs if they could simply describe their behaviors in natural language.…
Large language models (LLMs) are increasingly trained on massive, heterogeneous text corpora, raising serious concerns about the unauthorised use of proprietary or personal data during model training. In this work, we address the problem of…
The increasing availability of large language models (LLMs) has raised concerns about their potential misuse in online learning. While tools for detecting LLM-generated text exist and are widely used by researchers and educators, their…
The pre-training of large language models (LLMs) relies on massive text datasets sourced from diverse and difficult-to-curate origins. Although membership inference attacks and hidden canaries have been explored to trace data usage, such…
Large Language Models (LLMs) are trained on massive web-crawled corpora. This poses risks of leakage, including personal information, copyrighted texts, and benchmark datasets. Such leakage leads to undermining human trust in AI due to…
The rapid advancements of Large Language Models (LLMs) tightly associate with the expansion of the training data size. However, the unchecked ultra-large-scale training sets introduce a series of potential risks like data contamination,…